An Out-of-Core Method for CFD Simulation in Heterogeneous Environment

Article Preview

Abstract:

In recent years, the highly parallel graphics processing unit (GPU) is rapidly gaining maturity as a powerful engine for high performance computer. However, in most computational fluid dynamics (CFD) simulations, the computational capacity of CPU was ignored. In this paper, we propose a hybrid parallel programming model to utilize the computational capacity of both CPU and GPU. Considering the memory amount of CPU and GPU, we also propose an out-of-core method to increase the simulation scale on single node. The experiment results show that the programming model can utilize the computational capacity of both CPU and GPU efficiently and the out-of-core method can increase the simulation scale on single node.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 753-755)

Pages:

2912-2915

Citation:

Online since:

August 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Information on http: /www. top500. org/lists/2012/11.

Google Scholar

[2] Jacobsen, D., Thibault, J., Senocak, I., in: 48th AIAA Aerospace Sciences Meetings, Orlando, Florida (2010).

Google Scholar

[3] Appleyard, J., Drikakis, D.: Comput. Fluids Vol. 46 (2011), pp.101-105.

Google Scholar

[4] Wang, P., Abel, T., Kaehler, R.: New Astron. Vol. 15(2010), pp.581-589.

Google Scholar

[5] Griebel, M., Zaspel, P.: Comput. Sci. Res. Dev. Vol. 25(2010), pp.65-73.

Google Scholar

[6] Lu, F., Song, J., Cao, X., etc.: Comput. Fluids Vol. 41(2012), pp.47-55.

Google Scholar

[7] Yang, X.J., Liao, X.K., etc.: J. Comput. Sci. Technol. Vol. 26(2011), pp.344-351.

Google Scholar

[8] Xie, M., Lu, Y., etc. in: High Performance Interconnects (HOTI), 2011 IEEE 19th Annual Symposium on, Santa Clara, California(2011).

Google Scholar